© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4517
    Prev
    Next
    INDEX
    Explanations

    phrases related to the usage of methods or techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Word followed by "data" or a technique

    np_acts-logits-general · gemini-2.0-flash

    use / using / used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -1.11
    :✨
    -1.04
    WebVitals
    -1.01
    WriteTagHelper
    -0.98
     houſe
    -0.98
    saraba
    -0.96
     Houſe
    -0.95
     myſelf
    -0.94
    elemField
    -0.94
     crdi
    -0.93
    POSITIVE LOGITS
     a
    0.77
    fully
    0.70
     the
    0.70
    到的
    0.67
    FUL
    0.65
     
    0.60
     only
    0.59
     techniques
    0.55
    full
    0.55
    的是
    0.55
    Activations Density 0.276%

    No Known Activations